3 papers
cs.LG2026
Near-Optimal Cryptographic Hardness of Learning With Homogeneous Halfspaces Under Gaussian Marginals
Jizhou Huang, Brendan Juba
We study three problems that involve identifying homogeneous halfspaces under Gaussian distributions: agnostic learning, one-sided reliable learning, and fairness auditing. In each…
cs.LG2025
Personalized Prediction By Learning Halfspace Reference Classes Under Well-Behaved Distribution
Jizhou Huang, Brendan Juba
In machine learning applications, predictive models are trained to serve future queries across the entire data distribution. Real-world data often demands excessively complex model…
cs.LG2025
Distribution-Specific Agnostic Conditional Classification With Halfspaces
Jizhou Huang, Brendan Juba
We study ``selective'' or ``conditional'' classification problems under an agnostic setting. Classification tasks commonly focus on modeling the relationship between features and c…